Dynamic Flows on Curved Space Generated by Labeled Data

Abstract

The scarcity of labeled data is a long-standing challenge for many machine learning tasks. We propose our gradient flow method to leverage the existing dataset (i.e., source) to generate new samples that are close to the dataset of interest (i.e., target). We lift both datasets to the space of probability distributions on the feature-Gaussian manifold, and then develop a gradient flow method that minimizes the maximum mean discrepancy loss. To perform the gradient flow of distributions on the curved feature-Gaussian space, we unravel the Riemannian structure of the space and compute explicitly the Riemannian gradient of the loss function induced by the optimal transport metric. For practical applications, we also propose a discretized flow, and provide conditional results guaranteeing the global convergence of the flow to the optimum. We illustrate the results of our proposed gradient flow method on several real-world datasets and show our method can improve the accuracy of classification models in transfer learning settings.

References in corpus (7)

• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• The Cramer Distance as a Solution to Biased Wasserstein Gradients
• Geometric Dataset Distances via Optimal Transport
• Kernelized Wasserstein Natural Gradient
• Dataset Dynamics via Gradient Flows in Probability Space
• On the Convergence of Gradient Descent in GANs: MMD GAN As a Gradient Flow
• Generating Synthetic Datasets by Interpolating along Generalized Geodesics